{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 67,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 751.5826219558716,
      "epoch": 0.14925373134328357,
      "grad_norm": 0.05440790206193924,
      "kl": 0.0004100203514099121,
      "learning_rate": 2.981532510892707e-06,
      "loss": 0.0,
      "reward": 0.5398437750758603,
      "reward_std": 0.17991895689629017,
      "rewards/accuracy_reward": 0.5398437750758603,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 702.3262582778931,
      "epoch": 0.29850746268656714,
      "grad_norm": 0.06719266623258591,
      "kl": 0.003581857681274414,
      "learning_rate": 2.6657189421854562e-06,
      "loss": 0.0001,
      "reward": 0.638616100139916,
      "reward_std": 0.17700234022922814,
      "rewards/accuracy_reward": 0.638616100139916,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 691.965877532959,
      "epoch": 0.44776119402985076,
      "grad_norm": 0.05895258113741875,
      "kl": 0.005243682861328125,
      "learning_rate": 2.03755192431795e-06,
      "loss": 0.0002,
      "reward": 0.6462053855881095,
      "reward_std": 0.1541675410233438,
      "rewards/accuracy_reward": 0.6462053855881095,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 707.5672185897827,
      "epoch": 0.5970149253731343,
      "grad_norm": 0.058525312691926956,
      "kl": 0.0052001953125,
      "learning_rate": 1.2653483024396534e-06,
      "loss": 0.0002,
      "reward": 0.6322544911876321,
      "reward_std": 0.16165802334435284,
      "rewards/accuracy_reward": 0.6322544911876321,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "completion_length": 704.0386474609375,
      "epoch": 0.746268656716418,
      "grad_norm": 0.06317134201526642,
      "kl": 0.005251502990722657,
      "learning_rate": 5.560194134252441e-07,
      "loss": 0.0002,
      "reward": 0.646986634656787,
      "reward_std": 0.17009052280336617,
      "rewards/accuracy_reward": 0.646986634656787,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "completion_length": 707.1575080871582,
      "epoch": 0.8955223880597015,
      "grad_norm": 0.06633874773979187,
      "kl": 0.005028247833251953,
      "learning_rate": 9.962936025419756e-08,
      "loss": 0.0002,
      "reward": 0.6450893133878708,
      "reward_std": 0.16321602170355617,
      "rewards/accuracy_reward": 0.6450893133878708,
      "rewards/format_reward": 0.0,
      "step": 60
    },
    {
      "completion_length": 699.3392094203404,
      "epoch": 1.0,
      "kl": 0.005236353193010602,
      "reward": 0.6494473048618862,
      "reward_std": 0.16819066973403096,
      "rewards/accuracy_reward": 0.6494473048618862,
      "rewards/format_reward": 0.0,
      "step": 67,
      "total_flos": 0.0,
      "train_loss": 0.00016992172046474167,
      "train_runtime": 12440.6204,
      "train_samples_per_second": 0.603,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 10,
  "max_steps": 67,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}